{"id":"W4390116162","doi":"10.1016/j.cviu.2023.103906","title":"Learning feature contexts by transformer and CNN hybrid deep network for weakly supervised person search","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Discriminative model; Transformer; Feature (linguistics); Machine learning; Feature learning; Pattern recognition (psychology); Feature extraction; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003874599,0.000903198,0.001383797,0.0008980707,0.0004760492,0.0006986873,0.001477642,0.001065193,0.002907097],"category_scores_gemma":[0.001027841,0.0004440552,0.0008559501,0.001021026,0.0004274562,0.001676099,0.001659574,0.001187103,0.00145329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005694255,"about_ca_system_score_gemma":0.0009886237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056869,"about_ca_topic_score_gemma":0.01857423,"domain_scores_codex":[0.9995124,0.00006165967,0.00001955598,0.0002095878,0.00009276139,0.0001040153],"domain_scores_gemma":[0.9997552,0.00005125599,0.00002578321,0.00006864043,0.00006749415,0.00003169405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009380767,0.0006397811,0.005780348,0.0001979016,0.0001899714,0.0003333536,0.0001456231,0.1035815,0.0441645,0.009742299,0.01422731,0.8200594],"study_design_scores_gemma":[0.00001277269,0.00007815685,0.0007046316,0.0000101832,0.00002947062,0.0001061537,0.00002986663,0.9887164,0.004669748,0.004425188,0.001207802,0.000009568066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08600324,0.00109843,0.9054149,0.0002566414,0.0001437051,0.0001018133,0.0006227565,0.002906179,0.003452257],"genre_scores_gemma":[0.8388622,0.0006157707,0.1482112,0.0003718612,0.000139862,0.00008288629,0.002139352,0.000208947,0.009367943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01056869,"threshold_uncertainty_score":0.02101439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04349798754286054,"score_gpt":0.3042416187592012,"score_spread":0.2607436312163407,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}